作者: Hugo Proença , Luís A. Alexandre
DOI: 10.1016/J.IMAVIS.2009.03.003
关键词:
摘要: Iris recognition has been widely used in several scenarios with very satisfactory results. As it is one of the earliest stages, image segmentation basis process and plays a crucial role success task. In this paper we analyze relationship between accuracy iris error rates three typical methods. We selected 5000 images UBIRIS, CASIA ICE databases that algorithm can accurately segment artificially simulated four types inaccuracies. The obtained results allowed us to conclude about strong translational inaccuracies - lead errors phase rates.